Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6892. Min Range: -3.6892

Max Act: 3.6892. Min Act: -0.0000

Data Index: 1285735 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1137334 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.4239. Min Act: -0.0000

Data Index: 987888 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1691445 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1937729 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1950. Min Act: -0.0000

Data Index: 1235927 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1326366 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.2477. Min Act: -0.0000

Data Index: 1237784 (The Pile)

Max Activating Token Index: 127

Text #8

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1350. Min Act: -0.0000

Data Index: 537743 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.8736. Min Act: -0.0000

Data Index: 617908 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.8400. Min Act: -0.0000

Data Index: 1985104 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.0376. Min Act: -0.0000

Data Index: 379431 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.9178. Min Act: -0.0000

Data Index: 1095743 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.8986. Min Act: -0.0000

Data Index: 1971883 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.9643. Min Act: -0.0000

Data Index: 1572710 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.7277. Min Act: -0.0000

Data Index: 632622 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.7135. Min Act: -0.0000

Data Index: 1656809 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.6949. Min Act: -0.0000

Data Index: 1346415 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1220531 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.6443. Min Act: -0.0000

Data Index: 1961546 (The Pile)

Max Activating Token Index: 96